Our new X account is live! Follow @wizwand_team for updates

Summarization on WikiHow (test)

19.23ROUGE

Vanilla

Updated 4d ago

Evaluation Results

Method	Links
Vanilla 2025.12		19.23	-	-	-	-	-	85.52
Chain-of-Thought (CoT) 2025.12		19.2	-	-	-	-	-	85.46
Self-Consistency (SC) 2025.12		18.71	-	-	-	-	-	84.83
Cited Summarization (Cite) 2025.12		18.66	-	-	-	-	-	84.05
Iterative Refine (IR) 2025.12		18.4	-	-	-	-	-	85.2
Extract-to-Abstract (E2A) 2025.12		18.32	-	-	-	-	-	85.4
o1 2025.12		17.38	-	-	-	-	-	83.52
Decomposition (Deco) 2025.12		17.16	-	-	-	-	-	85.26
GPT-5 2025.12		16.41	-	-	-	-	-	84.06
o3 2025.12		16.31	-	-	-	-	-	84.61
Question-Answer Guided (QAG) 2025.12		16.25	-	-	-	-	-	84.39
Plan-then-Write (Plan) 2025.12		15.42	-	-	-	-	-	84.59
Gold 2022.11		-	4.72	4.57	4.87	4.88	-	-
GPT-3.5 2022.11		-	4.9	4.83	4.63	4.58	-	-
PEGASUS 2022.11		-	4.43	4.17	4.17	4.33	-	-
BART-PT 2022.11		-	4.3	4	3.93	4.17	-	-
UNISUMM 2022.11		-	4.68	4.43	4.67	4.67	-	-
Prior SOTA 2022.08		-	-	-	-	-	18.5	-
PEGASUS_LARGE 2022.08		-	-	-	-	-	18.5	-
Z-Code++_LARGE 2022.08		-	-	-	-	-	22.1	-